欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对现有的的车道线识别算法在复杂环境下识别率低、鲁棒性和实时性较差的问题,提出了一种基于形态学多结构元素建模的车道线快速识别算法。该算法首先对车道图像进行感兴趣区域提取,通过Canny算子对感兴趣区域进行边缘检测;然后利用具有车道模型特征的多结构元素进行车道线提取、霍夫变换,以及峰值检测点参数的筛选,从而得到实际车道左右标志线的参数以重建原车道线。仿真实验表明,该算法能在多种复杂环境下快速、准确地识别出车道标志线,且鲁棒性高。
英文摘要：
The existing lane recognition algorithms have low recognition ratio,bad robustness and real-time,for overcoming these drawbacks,this paper proposed a fast algorithm of lane recognition based on multi-structure elements model of morphological.In the algorithm,extracted the interested area from original image,which detected by the operator of Canny.After that,extracted the lanes by the structure elements,which had similar characteristics to that of lane model.Detected several lines by Hough transformation,and choose the parameters to reconstruct the traffic lane.Experiments show that this algorithm is simple,has better robustness,and at the same time,can efficiently detect the lane mask accurately and quickly.
同期刊论文项目
同项目期刊论文
期刊信息
位置：